Less is More: Robust Zero-Communication 3D Pursuit-Evasion via Representational Parsimony

TL;DR

This paper demonstrates that reducing the complexity of agent observations and using a locality-aware credit assignment improves robustness and performance in multi-agent pursuit-evasion tasks without communication.

Contribution

It introduces a representational parsimony approach with a simplified observation interface and Contribution-Gated Credit Assignment for communication-free coordination.

Findings

Achieves higher success rates than full observation models in pursuit-evasion tasks.

Maintains performance under various stress tests including noise and delays.

Shows resilience and transferability to urban environments.

Abstract

Asymmetric 3D pursuit-evasion in cluttered voxel environments is difficult under communication latency, partial observability, and nonholonomic maneuver limits. While many MARL methods rely on richer inter-agent coupling or centralized signals, these dependencies can become fragility sources when communication is delayed or noisy. Building on an inherited path-guided decentralized pursuit scaffold, we study a robustness-oriented question: can representational parsimony improve communication-free coordination? We instantiate this principle with (i) a parsimonious actor observation interface that removes team-coupled channels (83-D to 50-D), and (ii) Contribution-Gated Credit Assignment (CGCA), a locality-aware credit structure for communication-denied cooperation. In Stage-5 evaluation (4 pursuers vs. 1 evader), our configuration reaches 0.753 +/- 0.091 success and 0.223 +/- 0.066 collision, outperforming the 83-D FULL OBS counterpart (0.721 +/- 0.071, 0.253 +/- 0.089). It further shows graceful degradation under speed/yaw/noise/delay stress tests and resilient zero-shot transfer on urban-canyon maps (about 61% success at density 0.24). These results support a practical paradigm shift: explicitly severing redundant cross-agent channels can suppress compounding error cascades and improve robustness in latency-prone deployment.